Training in progress, step 4500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e34560d7ceb961c8ed1daafdbc8d29639fec0a982153daab41f97d4037611d
+oid sha256:71e295c3d1f676bfb0d3fd49cdc2cf71014ff519a6577b1e693b3d8da39745cc
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae19cfcaee886abb8174d3662413d49264385fe5c93861421f1cfa8344a7ffd8
+oid sha256:4f833405284ac2584aa0571b66b1efbd54f4bf68ae71c4ed62f10f5532985520
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c645775385b221b832715f20158171035bab79b5b82f53d47dfdb772e39b0bc8
+oid sha256:51a1858872f1d855aa2e9f6a605bc0f33fefd12a28a30c2dd4668559808db1d0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2081148219707423,
+  "epoch": 2.4841291747170855,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,41 @@
       "learning_rate": 6.845317470362014e-05,
       "loss": 0.154,
       "step": 4000
+    },
+    {
+      "epoch": 2.263317692520011,
+      "grad_norm": 0.7042354345321655,
+      "learning_rate": 6.664839324798001e-05,
+      "loss": 0.155,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3185205630692796,
+      "grad_norm": 0.8404821157455444,
+      "learning_rate": 6.481887122549755e-05,
+      "loss": 0.1576,
+      "step": 4200
+    },
+    {
+      "epoch": 2.373723433618548,
+      "grad_norm": 0.8974793553352356,
+      "learning_rate": 6.296732742177644e-05,
+      "loss": 0.1553,
+      "step": 4300
+    },
+    {
+      "epoch": 2.428926304167817,
+      "grad_norm": 0.8145149350166321,
+      "learning_rate": 6.109651334818204e-05,
+      "loss": 0.1542,
+      "step": 4400
+    },
+    {
+      "epoch": 2.4841291747170855,
+      "grad_norm": 0.9313832521438599,
+      "learning_rate": 5.9209209152921384e-05,
+      "loss": 0.1541,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -306,7 +341,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1211958631160873e+18,
+  "total_flos": 2.388204789671264e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null